Modelling the effect of speaker familiarity and noise on infant word recognition

In the present paper we show that a general-purpose word learn­ ing model can simulate several important findings from recent experiments in language acquisition. Both the addition of back­ ground noise and varying the speaker have been found to in­ fluence infants’ performance during word recognition experi­ ments. We were able to replicate this behaviour in our artificial word learning agent. We use the results to discuss both ad­ vantages and limitations of computational models of language acquisition.